Using Anthropic Chat Completion

interface Request {
	model: string;
	messages: {
		role: 'user' | 'assistant' | 'system' | 'function';
		content: string;
		name?: string;
		function_call?: object;
	}[];
	max_tokens_to_sample?: number;
	temperature?: number;
	top_p?: number;
	top_k?: number;
};

{
    "model": "claude-instant-1",
    "messages": [
        {
            "role": "user",
            "content": "Hello, who are you?"
        },
        {
            "role": "assistant",
            "content": "I'm Claude, an AI assistant. How can I help you today?"
        },
        {
            "role": "user",
            "content": "Can you explain what an API is?"
        }
    ]
}

interface Response {
	id: string;
	created: number;
	model: string;
	choices: [
		{
			index: number;
			message: {
				role: 'assistant',
				content: string;
			};
			finish_reason: any;
		}
	];
};

{
    "id": "c20ccfc2db49ca08b17b0b47ddb29ea6bdb750beb7dc146f17fcfb94a9beaf56",
    "object": "chat.completion",
    "created": 1690391419,
    "model": "claude-instant-1.1",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "An API (Application Programming Interface) is a set of rules that lets software applications communicate with each other."
            },
            "finish_reason": "stop_sequence"
        }
    ]
}